Product & Machine Learning
Clinical Research & Business Development
Product & ML meets Clinical Research & Business Development. ClinAssist is built by people who understand both sides of the trust gap.
Two UNSW graduates tackling the hardest problem in clinical AI — not the model, but the trust.
Product & ML
Computer Science graduate from UNSW with hands-on experience in machine learning, explainability, and clinical AI. Sri leads the technical architecture and ML pipeline — from EHR ingestion and SHAP explainability to the clinician-facing interface. The focus is entirely on shipping something real: a validated prototype that solves the adoption gap that has held clinical AI back for a decade.
"The hardest problem in clinical AI isn't accuracy — it's trust. A model that can't explain itself will never be used, no matter how good it is."
Clinical & BD
Santosh bridges the gap between the model and the clinician. He leads structured clinician engagement, clinical validation research, and hospital partnership development — ensuring ClinAssist is built around real workflows, not hypothetical ones. His work ensures every design decision is grounded in what clinicians actually need at the point of care.
"We don't just need better models. We need to understand why clinicians don't use them — and design from that truth."
Clinical Advisor
Dr. Shankar Reddy brings frontline clinical perspective to ClinAssist. As a practicing clinician, he advises on real-world ED and ICU workflows, clinical decision-making under pressure, and the practical barriers that prevent AI tools from being adopted at the point of care. His insights directly shape how ClinAssist presents information to time-pressured clinicians.
"What clinicians need isn't more data — it's the right signal, at the right moment, explained in a way they can act on."
Legal Advisor
Taruni brings critical legal and regulatory expertise to ClinAssist. With a dual background in business and law, she advises on TGA compliance, Australian Privacy Act obligations, health data governance, and the regulatory frameworks governing AI as a Medical Device. Her guidance ensures ClinAssist is built with compliance as a foundation, not an afterthought.
"In health AI, regulatory trust and clinical trust go hand in hand. Getting the legal framework right from day one isn't optional — it's the product."
A milestone-driven plan with measurable outcomes at every stage — from dataset to deployment.
ClinAssist concept developed. Problem space validated against clinical literature and real-world adoption data. Technical architecture defined. Team formed. Website and public presence launched.
Systematic review of clinical AI and XAI literature. Structured clinician interviews to identify highest-priority decision support needs. TGA regulatory scoping. IRB/ethics approval and dataset access confirmed (MIMIC-IV, PhysioNet).
XGBoost + SHAP pipeline on structured EHR data. Transformer NLP on clinical notes. CNN/ViT imaging pipeline. Unified risk scoring interface prototype.
Human-factors evaluation with ED clinicians. Does SHAP/LIME/attention-based explainability improve decision accuracy and clinician trust vs. no-explanation baseline? Santosh leads clinician recruitment and study design.
Two target peer-reviewed publications: one on model architecture, one on clinical validation methodology. Open-source ClinAssist prototype released for hospital piloting and further research. Target venues: JAMIA, npj Digital Medicine. Active engagement with NSW Health and prospective clinical partners.
Whether you're a clinician, investor, or health institution — we want to hear from you.
Interested in piloting or providing feedback on ClinAssist in your ED or ICU
Backing the team building explainable clinical AI for Australia and beyond
Health institutions, researchers, and technology partners who share the mission